Nvidia – Llama Nemotron Ultra 253B

2025-04-10

🎊 Llama Nemotron Ultra 253B is here 🎊

✅ 4x higher inference throughput over DeepSeek R1 671B

🏆Highest accuracy on reasoning benchmarks:
💎 GPQA-Diamond for advanced scientific reasoning
💎 AIME 2024/25 for complex math
💎 LiveCodeBench for code generation and completion… pic.twitter.com/oxgyhBkQGd
— NVIDIA AI Developer (@NVIDIAAIDev) April 8, 2025

Links

Announcement: https://developer.nvidia.com/blog/build-enterprise-ai-agents-with-advanced-open-nvidia-llama-nemotron-reasoning-models/?ncid=so-twit-441150

Videos